great graphic – is there a canonical source for the gpt3 family tree or did you just come up with this? (want to make sure i cite properly when i definitely use this in future)
LLMS
-
RLHF automates human evaluation and generates tuning data
By
–
Later, reinforcement learning was used to automate the task of human evaluation as well. This yielded a endless fountain of tuning data that could be produced entirely by machine — a process known as RLHF.
-
Tuning models on filtered self-generations for smarter AI
By
–
By tuning the model on its own generations, filtered to those deemed perfect by human evaluators, greater volumes of data could be used, yielding a more intelligent and obedient model.
-
Human demonstrations limited early instruction tuning models
By
–
Early attempts at instruction tuning relied entirely on demonstrations from humans. This made the model easier to prompt, but the approach was limited by the inherent difficulty of manufacturing new humans.
-
Model Evaluations Counting Details Fine Print Clarification
By
–
Good point – the fine print states we're actually counting model evals
-
Instruction tuning merges human will into AI controlled by awkward kid
By
–
Instruction tuning / RLHF is technically a Human Instrumentality Project, merging the preferences of countless humans to form an oversized, living amalgam of our will. We then hand control of it to a random, socially awkward kid and hope for the best.
-
UC Berkeley and Peking U Propose Unsupervised Contrast-Consistent Search
By
–
Finding Truth in LLMs: UC Berkeley & Peking U Propose Unsupervised Contrast-Consistent Search https://
syncedreview.com/2022/12/14/fin
ding-truth-in-llms-uc-berkeley-peking-u-propose-unsupervised-contrast-consistent-search/
… -
Fine-tuned Models Testing on Public Datasets
By
–
Interesting. What kind of data are you inferring on? Is there some publicly available data that you’re testing on? Would love to test out some of our fine-tuned models against it.
-
Prompt Engineering: Better Results Working Directly With Models
By
–
No longer using ChatGPT super often. As a diehard prompt engineer, I can nearly always get better results by working with the models directly. BUT For the average person, chat is the best and easiest way to get language models to do what you want. Conversation is prompting.
